将 Book-Crossing Dataset 书籍推荐算法中 CVS 格式测试数据集导入到MySQL数据库
本文内容
最近看《写给程序员的数据挖掘指南》，研究推荐算法，书中的测试数据集是 Book-Crossing Dataset 提供的亚马逊用户对书籍评分的真实数据。推荐大家看本书，写得不错，立刻就能对推荐算法上手，甚至应用到你的项目中。
Book-Crossing Dataset 提供两种格式的数据集：CVS 格式和 SQL dump，问题是：
如果你有 UE 打开 cvs 文件，有乱码。无论如何转换编码，都不行~因为，这个文件是亚马逊通过程序持久化后，再导出来的。你还会发现，文件中有 html 标记，另外，关于用户名，书名等等信息，基本都是德文的（看域名就知道了）~
虽然，作者提供了加载测试数据集的 python 代码，不过不能导入到 MySQL 数据库中，其中，作者只是简单地按分号来分割字段内容（虽然推荐算法并不需要全部字段），可数据集中包含类似“ऩ”或“\“”这样的字符，不可能导入到 MySQL 数据库中~
你也许会问，作者都不导入到数据库，你为什么要导？因为，作者提供的推荐算法属于内存模型，也就是一次性把数据加载到内存，但之前，总还是要持久化吧~
因此，只能改造一下作者的 Python 代码~
Github Demo
改造后测试数据集
Python
# -*- coding: utf-8 -*-
import mysql.connector
import codecs
import string
import os
import sys
import ConfigParser
from collections import OrderedDict
import re
class MysqlPythonFacotry(object):
"""
Python Class for connecting with MySQL server.
"""
__instance = None
__host = None
__user = None
__password = None
__database = None
__session = None
__connection = None
def __init__(self, host='localhost', user='root', password='', database=''):
self.__host = host
self.__user = user
self.__password = password
self.__database = database
## End def __init__
def open(self):
try:
cnx = mysql.connector.connect(host=self.__host,\
user= self.__user,\
password= self.__password,\
database= self.__database)
self.__connection = cnx
self.__session = cnx.cursor()
except mysql.connector.Error as e:
print('connect fails!{}'.format(e))
## End def open
def close(self):
self.__session.close()
self.__connection.close()
## End def close
def select(self, table, where=None, *args, **kwargs):
result = None
query = 'SELECT '
keys = args
values = tuple(kwargs.values())
l = len(keys) - 1
for i, key in enumerate(keys):
query += "`" + key + "`"
if i <; l:
query += ","
## End for keys
query += 'FROM %s' % table
if where:
query += " WHERE %s" % where
## End if where
self.__session.execute(query, values)
number_rows = self.__session.rowcount
number_columns = len(self.__session.description)
result = self.__session.fetchall()
return result
## End def select
def update(self, table, where=None, *args, **kwargs):
try:
query = "UPDATE %s SET " % table
keys = kwargs.keys()
values = tuple(kwargs.values()) + tuple(args)
l = len(keys) - 1
for i, key in enumerate(keys):
query += "`" + key + "` = %s"
if i <; l:
query += ","
## End if i less than 1
## End for keys
query += " WHERE %s" % where
self.__session.execute(query, values)
self.__connection.commit()
# Obtain rows affected
update_rows = self.__session.rowcount
except mysql.connector.Error as e:
print(e.value)
return update_rows
## End function update
def insert(self, table, *args, **kwargs):
values = None
query = "INSERT INTO %s " % table
if kwargs:
keys = kwargs.keys()
values = tuple(kwargs.values())
query += "(" + ",".join(["`%s`"] * len(keys)) % tuple(keys) + ") VALUES (" + ",".join(["%s"] * len(values)) + ")"
elif args:
values = args
query += " VALUES(" + ",".join(["%s"] * len(values)) + ")"
self.__session.execute(query, values)
self.__connection.commit()
cnt = self.__session.rowcount
return cnt
## End def insert
def delete(self, table, where=None, *args):
query = "DELETE FROM %s" % table
if where:
query += ' WHERE %s' % where
values = tuple(args)
self.__session.execute(query, values)
self.__connection.commit()
delete_rows = self.__session.rowcount
return delete_rows
## End def delete
def select_advanced(self, sql, *args):
od = OrderedDict(args)
query = sql
values = tuple(od.values())
self.__session.execute(query, values)
number_rows = self.__session.rowcount
number_columns = len(self.__session.description)
result = self.__session.fetchall()
return result
## End def select_advanced
## End class
class ErrorMyProgram(Exception):
"""
My Exception Error Class
"""
def __init__(self, value):
self.value = value
##End def __init__
def __str__(self):
return repr(self.value)
##End def __str__
## End class ErrorMyProgram
class LoadAppConf(object):
"""
Load app.conf Config File Class
"""
__configFileName = "app.conf"
def __init__(self):
config = ConfigParser.ConfigParser()
config.read(self.__configFileName)
self.biz_db_host = config.get("biz_db","host")
self.biz_db_user = config.get("biz_db","user")
self.biz_db_password = config.get("biz_db","password")
self.biz_db_database = config.get("biz_db","database")
## End def __init__
## End class LoadAppConf
class Biz_Base(object):
"""
biz base class
"""
def __init__(self, db):
self.db = db
## End def __init__
## End class Biz_Base
class Biz_bx_book_ratings(Biz_Base):
"""
bx_book_ratings table
"""
__tableName = "bx_book_ratings"
def __init__(self, db):
Biz_Base.__init__(self, db)
## End def __init__
def insert(self, userid, isbn, bookrating):
cnt = self.db.insert(self.__tableName,\
userid = userid, \
isbn = isbn,\
bookrating = bookrating)
return cnt >; 0
## End def insert
## End class Biz_bx_book_ratings
class Biz_bx_books(Biz_Base):
"""
bx_books table
"""
__tableName = "bx_books"
def __init__(self, db):
Biz_Base.__init__(self, db)
## End def __init__
def insert(self, isbn, booktitle, bookauthor, yearofpublication, publisher, imageurls, imageurlm, imageurll):
cnt = self.db.insert(self.__tableName,\
isbn = isbn, \
booktitle = booktitle, \
bookauthor = bookauthor,\
yearofpublication = yearofpublication, \
publisher = publisher, \
imageurls = imageurls, \
imageurlm = imageurlm, \
imageurll = imageurll)
return cnt >; 0
## End def insert
## End class Biz_bx_books
class Biz_bx_users(Biz_Base):
"""
bx_users table
"""
__tableName = "bx_users"
def __init__(self, db):
Biz_Base.__init__(self, db)
## End def __init__
def insert(self, userid, location, age):
cnt = self.db.insert(self.__tableName,\
userid = userid, \
location = location,\
age = age)
return cnt >; 0
## End def insert
## End class Biz_bx_users
def regx(l):
"""
split line by regex
"""
p = re.compile(r'"[^"]*"')
return p.findall(l)
## End def regx
class LoadDataset(object):
"""
bx_books table
"""
__loadConf = None
__users = None
__books = None
__book_ratings = None
__bizDb = None
def __init__(self):
self.__loadConf = LoadAppConf()
self.__bizDb = MysqlPythonFacotry(self.__loadConf.biz_db_host,\
self.__loadConf.biz_db_user, \
self.__loadConf.biz_db_password,\
self.__loadConf.biz_db_database)
self.__users = Biz_bx_users(self.__bizDb)
self.__books = Biz_bx_books(self.__bizDb)
self.__book_ratings = Biz_bx_book_ratings(self.__bizDb)
self.__bizDb.open()
## End def __init__
def toDB(self, path=''):
"""
loads the BX book dataset. Path is where the BX files are
located
"""
self.data = {}
i = 0
j = 0
try:
#
# First load book ratings into self.data
#
f = codecs.open(path + "BX-Book-Ratings.csv", 'r', 'utf8')
for line in f:
i += 1
j += 1
print(j)
print(line)
#separate line into fields
fields = line.split(';')
user = fields[0].strip('"')
book = fields[1].strip('"')
rating = int(fields[2].strip().strip('"'))
self.__book_ratings.insert(user, book, rating)
f.close()
#
# Now load books into self.productid2name
# Books contains isbn, title, and author among other fields
#
j = 0
f = codecs.open(path + "BX-Books.csv", 'r', 'utf8')
for line in f:
i += 1
j += 1
print(j)
print(line)
#separate line into fields
fields = regx(line)
isbn = fields[0].strip('"')
title = fields[1].strip('"')
author = fields[2].strip().strip('"')
yearOfPublication = fields[3].strip().strip('"')
publisher = fields[4].strip().strip('"')
imageUrlS = fields[5].strip().strip('"')
imageUrlM = fields[6].strip().strip('"')
imageUrlL = fields[7].strip().strip('"')
self.__books.insert(isbn, title, author, yearOfPublication, publisher, imageUrlS, imageUrlM, imageUrlL)
f.close()
#
# Now load user info into both self.userid2name and
# self.username2id
#
j = 0
f = codecs.open(path + "BX-Users.csv", 'r', 'utf8')
for line in f:
i += 1
j += 1
print(j)
print(line)
#separate line into fields
fields = regx(line)
userid = fields[0].strip('"')
location = fields[1].strip('"')
if len(fields) >; 2:
age = fields[2].strip().strip('"')
else:
age = None
if age != None:
value = location + ' (age: ' + age + ')'
else:
value = location
if age == None:
age =0
self.__users.insert(userid, location, age)
f.close()
except ErrorMyProgram as e:
print(e.value)
finally:
self.__bizDb.close()
print(i)
## End def toDB
## End class LoadData
Github Demo
测试数据集
将 Book-Crossing Dataset 书籍推荐算法中 CVS 格式测试数据集导入到MySQL数据库的更多相关文章
- 用JDBC把Excel中的数据导入到Mysql数据库中
步骤:0.在Mysql数据库中先建好table 1.从Excel表格读数据 2.用JDBC连接Mysql数据库 3.把读出的数据导入到Mysql数据库的相应表中 其中,步骤0的table我是先在Mys ...
- SQL自连接（源于推荐算法中的反查表问题）
”基于用户的协同过滤算法“是推荐算法的一种,这类算法强调的是:把和你有相似爱好的其他的用户的物品推荐给你. 要实现该推荐算法,就需要计算和你有交集的用户,这就要用到物品到用户的反查表. 先举个例子说明 ...
- Attention机制在深度学习推荐算法中的应用(转载)
AFM:Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Ne ...
- Access数据库导入到mysql数据库中
做项目时需要查询手机号归属地的,用网上提供的接口,耗时太长,反应慢,只能自己在网上搜了一个包含所有手机号归属地的Access数据库,导入到自己的mysql数据库中 Access数据库导入到mysql中 ...
- 虚拟机中ubuntu-16.04 Linux系统下配置mysql数据库，并在windows下使用navicat远程连接
Linux系统下mysql数据库安装配置步骤: 1.在服务器上安装mysql:sudo apt-get install mysql-server sudo apt-get install mysql- ...
- 如何用java POI将word中的内容导入到mysql数据库中
由于作业需要,要求我们将word文档中的数据直接导入到mysql中,在网上找了很常时间,终于将其解决. 由于比较初级,所以处理的word文档是那种比较规范的那种,条例比较清晰,设计的思路也比较简单,就 ...
- MySQL中 如何查询表名中包含某字段的表 ,查询MySql数据库架构信息：数据库，表，表字段
--查询tablename 数据库中 以"_copy" 结尾的表 select table_name from information_schema.tables where ta ...
- 将Hive统计分析结果导入到MySQL数据库表中（一）——Sqoop导入方式
https://blog.csdn.net/niityzu/article/details/45190787 交通流的数据分析,需求是对于海量的城市交通数据,需要使用MapReduce清洗后导入到HB ...
- php中ip转int 并存储在mysql数据库
遇到一个问题,于是百度一下. 得到最佳答案 http://blog.163.com/metlive@126/blog/static/1026327120104232330131/ 如何将四个字 ...
随机推荐
- 组合（composition）与继承（inheritance）
c++中一个重要的特点就是代码的重用,为了代码重用,有两个非常重要的手段,一个是继承,一个是组合 上面两种类的关系就分别是继承和组合.下面我们看一下代码示例: #ifndef USEFUL_H #de ...
- LeetCode（84） Largest Rectangle in Histogram
题目 Given n non-negative integers representing the histogram’s bar height where the width of each bar ...
- P1093 奖学金
奖学金 题目描述 某小学最近得到了一笔赞助,打算拿出其中一部分为学习成绩优秀的前5名学生发奖学金.期末,每个学生都有3门课的成绩:语文.数学.英语.先按总分从高到低排序,如果两个同学总分相同,再按语文 ...
- 【转】APNs消息推送完整讲解
https://developer.apple.com/library/ios/#documentation/NetworkingInternet/Conceptual/RemoteNotificat ...
- git flow的安装和使用
确保安装了git 1.windows系统下安装 进入cmd clone github上的gitflow到一个文件夹下 我这里clone到 c:\gitflow git clone git://gith ...
- Matlab神经网络函数newff()新旧用法差异
摘要 在Matlab R2010a版中,如果要创建一个具有两个隐含层.且神经元数分别为5.3的前向BP网络,使用旧的语法可以这样写: net1 = newff(minmax(P), [5 3 1]); ...
- 从DB灌值到DataTable时，字段值为NULL时报错相关信息；
报错信息: 1. 2. 3. 4. 5. 6. 解决方法: 1. Data Layer SQL 语句取数据时,把其列值有为null的字段用0.00替换,(ISNULL的用法): 2. #r ...
- java编程规范
一.规范存在的意义 应用编码规范对于软件本身和软件开发人员而言尤为重要,有以下几个原因: 1.好的编码规范可以尽可能的减少一个软件的维护成本 , 并且几乎没有任何一个软件,在其整个生命周期中,均由最初 ...
- “SSLError: The read operation timed out” when using pip
Downloading/unpacking Django>=1.5.1,<1.6 (from -r requirements.txt (line 1)) Downloading Djang ...
- 通俗易懂的深入理解js闭包
闭包(closure)是Javascript语言的一个难点,也是它的特色,很多高级应用都要依靠闭包实现. 一.变量的作用域 要理解闭包,首先必须理解Javascript特殊的变量作用域. 变量的作用域 ...